arabert_baseline_mechanics_task1_fold1

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5507
• Qwk: 0.4324
• Mse: 0.5505

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse
No log	0.3333	2	4.9042	0.0	4.9234
No log	0.6667	4	2.0020	-0.0299	2.0282
No log	1.0	6	1.2914	0.0769	1.3136
No log	1.3333	8	1.0020	0.0500	1.0184
No log	1.6667	10	0.7738	0.125	0.7839
No log	2.0	12	0.8249	0.2105	0.8327
No log	2.3333	14	1.0118	0.0851	1.0228
No log	2.6667	16	0.7586	0.1905	0.7651
No log	3.0	18	0.4977	0.375	0.5025
No log	3.3333	20	0.5065	0.3429	0.5107
No log	3.6667	22	0.5186	0.4118	0.5205
No log	4.0	24	0.7202	0.2564	0.7199
No log	4.3333	26	0.6120	0.3889	0.6080
No log	4.6667	28	0.5684	0.3784	0.5637
No log	5.0	30	0.5531	0.3889	0.5482
No log	5.3333	32	0.6399	0.3784	0.6320
No log	5.6667	34	0.8218	0.2632	0.8129
No log	6.0	36	0.8057	0.2632	0.7976
No log	6.3333	38	0.6262	0.3784	0.6183
No log	6.6667	40	0.6028	0.3889	0.5950
No log	7.0	42	0.6011	0.3889	0.5943
No log	7.3333	44	0.6488	0.3158	0.6438
No log	7.6667	46	0.5939	0.3158	0.5907
No log	8.0	48	0.5456	0.4324	0.5440
No log	8.3333	50	0.5191	0.4324	0.5183
No log	8.6667	52	0.4890	0.4324	0.4889
No log	9.0	54	0.4994	0.4324	0.4996
No log	9.3333	56	0.5265	0.4324	0.5267
No log	9.6667	58	0.5469	0.4324	0.5468
No log	10.0	60	0.5507	0.4324	0.5505

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1